fix: make installed wheel self-contained + harden install.sh prereqs

Addresses the review on PR #481.

Self-contained wheel (review point 1): the gateway/infra/orchestrator
images build from a context that must hold bot_bottle/, pyproject.toml,
and the root-level Dockerfiles. Modules previously located these by
walking __file__ to the repo root, so an installed wheel (package in
site-packages, no repo root) passed `doctor` but failed `start`.

- Add bot_bottle/resources.py: build_root() returns the repo root in a
  checkout (unchanged) or a staged copy from the wheel's bundled
  _resources/ otherwise; dockerfile()/nix_netpool_module()/
  netpool_script() derive from it.
- setup.py bundles the root Dockerfiles, nix module, netpool script, and
  pyproject.toml into bot_bottle/_resources/ at build; MANIFEST.in ships
  them in the sdist.
- Route every _REPO_ROOT/_REPO_DIR call site (docker/macos launch, macos
  infra, firecracker infra_vm/infra_artifact/setup, orchestrator
  lifecycle/gateway) through resources. Checkout behavior is unchanged.

install.sh prerequisites (review point 2): check for git when installing
a git+ spec, and — before the pip fallback — that pip is usable and the
interpreter isn't externally managed (PEP 668), pointing at pipx.

Tests: test_resources covers checkout + staged-wheel layouts;
test_wheel_install builds the wheel, installs it into an isolated venv,
and asserts `doctor` runs and build_root() yields a valid context.
Running `start` end-to-end still needs a Docker/KVM host (CI).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-26 00:04:35 +00:00
committed by didericis
parent 955cb3bcbd
commit 1a4b390e8a
25 changed files with 675 additions and 52 deletions
+8 -4
View File
@@ -10,9 +10,10 @@ from ...paths import (
ORCHESTRATOR_AUTH_JWT_ENV,
host_gateway_ca_dir,
)
from ... import resources
from ...gateway import (
Gateway, GatewayTransport, GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK,
GATEWAY_DOCKERFILE, REPO_ROOT, GATEWAY_LABEL, MITMPROXY_HOME,
GATEWAY_DOCKERFILE, GATEWAY_LABEL, MITMPROXY_HOME,
DEFAULT_CA_TIMEOUT_SECONDS, CA_POLL_SECONDS, GATEWAY_CA_CERT, GatewayError
)
@@ -50,7 +51,9 @@ class DockerGateway(Gateway):
# `address` / `stop` work on an already-running gateway without it.
self._orchestrator_url = ""
self._gateway_token = ""
self._build_context = build_context or REPO_ROOT
# Resolved lazily in ensure_built() so merely constructing a gateway to
# read its CA never stages a build root from an installed wheel.
self._build_context = build_context
self._dockerfile = dockerfile
# Ports published on the host (0.0.0.0). Used by the Firecracker
# backend's dev-harness gateway so VMs can reach it via their TAP link;
@@ -72,9 +75,10 @@ class DockerGateway(Gateway):
forces a full rebuild (parity with `start --no-cache`)."""
if self._dockerfile is None:
return
context = self._build_context or resources.build_root()
argv = ["docker", "build", "-t", self.image_ref,
"-f", str(self._build_context / self._dockerfile),
str(self._build_context)]
"-f", str(context / self._dockerfile),
str(context)]
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
argv.insert(2, "--no-cache")
proc = run_docker(argv)
+5 -4
View File
@@ -34,6 +34,7 @@ from .orchestrator import (
ORCHESTRATOR_NETWORK,
)
from ...paths import bot_bottle_root
from ... import resources
from ...gateway import (
GATEWAY_IMAGE,
GATEWAY_NAME,
@@ -50,8 +51,6 @@ from ...orchestrator.lifecycle import (
# the pair's public identity.
INFRA_NAME = GATEWAY_NAME # the container agents attribute against is the gateway
_REPO_ROOT = Path(__file__).resolve().parents[3]
class DockerInfraService(InfraService):
"""Composes the per-host control plane + gateway as two containers.
@@ -68,7 +67,7 @@ class DockerInfraService(InfraService):
control_network: str = ORCHESTRATOR_NETWORK,
orchestrator_image: str = ORCHESTRATOR_IMAGE,
gateway_image: str = GATEWAY_IMAGE,
repo_root: Path = _REPO_ROOT,
repo_root: Path | None = None,
host_root: Path | None = None,
orchestrator_name: str = ORCHESTRATOR_NAME,
orchestrator_label: str = ORCHESTRATOR_LABEL,
@@ -79,7 +78,9 @@ class DockerInfraService(InfraService):
self.control_network = control_network
self.orchestrator_image = orchestrator_image
self.gateway_image = gateway_image
self._repo_root = repo_root
# Build context / bind-mount source: the repo root in a checkout, a
# staged copy from the installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._host_root = host_root or bot_bottle_root()
self._orchestrator_name = orchestrator_name
self._orchestrator_label = orchestrator_label
+2 -6
View File
@@ -33,7 +33,6 @@ from __future__ import annotations
import dataclasses
import os
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...agent_provider import runtime_for
@@ -65,10 +64,7 @@ from ...orchestrator.store.config_store import resolve_teardown_timeout
from .consolidated_launch import launch_consolidated, deprovision_consolidated
from .infra import INFRA_NAME
from .gateway import DockerGateway
# Where the repo root lives, for `docker build` context. Computed once.
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
from ... import resources
def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
@@ -88,7 +84,7 @@ def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
)
info(f"using cached agent image {plan.image!r}")
return BottleImages(agent=plan.image)
docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
docker_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
docker_mod.verify_agent_image(
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
)
+5 -4
View File
@@ -15,6 +15,7 @@ import time
from pathlib import Path
from ... import log
from ... import resources
from .util import run_docker
from ...paths import (
ORCHESTRATOR_TOKEN_ENV,
@@ -55,8 +56,6 @@ _ROOT_IN_CONTAINER = "/bot-bottle-root"
_HEALTH_POLL_SECONDS = 0.25
_REPO_ROOT = Path(__file__).resolve().parents[3]
class DockerOrchestrator(Orchestrator):
"""The control plane as a single fixed-name container. `ensure_built` builds
@@ -71,7 +70,7 @@ class DockerOrchestrator(Orchestrator):
label: str = ORCHESTRATOR_LABEL,
port: int = DEFAULT_PORT,
control_network: str = ORCHESTRATOR_NETWORK,
repo_root: Path = _REPO_ROOT,
repo_root: Path | None = None,
host_root: Path | None = None,
dockerfile: str | None = ORCHESTRATOR_DOCKERFILE,
) -> None:
@@ -80,7 +79,9 @@ class DockerOrchestrator(Orchestrator):
self.label = label
self.port = port
self.control_network = control_network
self._repo_root = repo_root
# Build context / bind-mount source: the repo root in a checkout, a
# staged copy from the installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._host_root = host_root or bot_bottle_root()
self._dockerfile = dockerfile
@@ -37,6 +37,7 @@ import urllib.error
import urllib.request
from pathlib import Path
from ... import resources
from ...log import die, info
from . import util
@@ -44,8 +45,6 @@ from . import util
# scheme can't collide with a cached/published artifact of the old one.
_ARTIFACT_FORMAT = "1"
_REPO_ROOT = Path(__file__).resolve().parents[3]
# The two per-plane infra VM roles. Each publishes/pulls its own rootfs artifact
# from its own generic package; the Dockerfiles baked into each differ (only the
# orchestrator rootfs carries buildah), so the versions are hashed separately.
@@ -74,7 +73,7 @@ def local_build_requested() -> bool:
def infra_artifact_version(
init_script: str, role: str, *, repo_root: Path = _REPO_ROOT,
init_script: str, role: str, *, repo_root: Path | None = None,
) -> str:
"""Content hash (16 hex) of everything baked into `role`'s infra rootfs: the
whole shipped `bot_bottle` package, that role's Dockerfiles, and its guest
@@ -89,6 +88,8 @@ def infra_artifact_version(
version or a launch host could boot a stale rootfs whose code differs from
its checkout. `__pycache__`/`.pyc` are the only exclusions — build artifacts,
never copied."""
if repo_root is None:
repo_root = resources.build_root()
h = hashlib.sha256()
h.update(f"format={_ARTIFACT_FORMAT}\nrole={role}\n".encode())
pkg = repo_root / "bot_bottle"
+5 -4
View File
@@ -42,6 +42,7 @@ from dataclasses import dataclass
from pathlib import Path
from typing import Generator
from ... import resources
from ...log import die, info
from ..docker import util as docker_mod
from . import firecracker_vm, infra_artifact, netpool, util
@@ -65,7 +66,6 @@ _GUEST_GATEWAY_JWT_PATH = "/var/lib/bot-bottle/gateway-jwt"
_GATEWAY_IMAGE = "bot-bottle-gateway:latest"
_ORCHESTRATOR_IMAGE = "bot-bottle-orchestrator:latest"
_ORCHESTRATOR_FC_IMAGE = "bot-bottle-orchestrator-fc:latest"
_REPO_ROOT = Path(__file__).resolve().parents[3]
# Per-role rootfs source image + the extra free space `mke2fs` leaves for the
# guest to grow into. The orchestrator keeps buildah's large build slack; the
@@ -130,12 +130,13 @@ def build_infra_images_with_docker() -> None:
orchestrator + buildah). The gateway VM boots the gateway image directly.
The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local` mode;
`publish_infra` uses it off-host to produce the published artifacts."""
root = str(resources.build_root())
docker_mod.build_image(
_ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
_ORCHESTRATOR_IMAGE, root, dockerfile="Dockerfile.orchestrator")
docker_mod.build_image(
_GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
_GATEWAY_IMAGE, root, dockerfile="Dockerfile.gateway")
docker_mod.build_image(
_ORCHESTRATOR_FC_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator.fc")
_ORCHESTRATOR_FC_IMAGE, root, dockerfile="Dockerfile.orchestrator.fc")
def build_rootfs_dir(role: str) -> Path:
+5 -4
View File
@@ -20,6 +20,7 @@ import subprocess
import sys
from pathlib import Path
from ... import resources
from . import netpool
from . import util
@@ -42,13 +43,13 @@ def _has_systemd() -> bool:
def _module_path() -> str:
"""Absolute path to the importable NixOS module in this checkout."""
return str(Path(__file__).resolve().parents[3] / "nix" / "firecracker-netpool.nix")
"""Absolute path to the importable NixOS module (checkout or wheel)."""
return str(resources.nix_netpool_module())
def _script_path() -> str:
"""Absolute path to the bundled bring-up script in this checkout."""
return str(Path(__file__).resolve().parents[3] / "scripts" / "firecracker-netpool.sh")
"""Absolute path to the bundled bring-up script (checkout or wheel)."""
return str(resources.netpool_script())
def _print_prereqs() -> None:
@@ -28,6 +28,7 @@ from ...paths import (
ORCHESTRATOR_AUTH_JWT_ENV,
host_gateway_ca_dir,
)
from ... import resources
from .. import util as backend_util
from . import util as container_mod
@@ -52,8 +53,6 @@ GATEWAY_DAEMONS = "egress,git-http,supervise"
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
_REPO_ROOT = Path(__file__).resolve().parents[3]
def ensure_networks(
network: str = GATEWAY_NETWORK,
@@ -84,14 +83,16 @@ class MacosGateway(Gateway):
network: str = GATEWAY_NETWORK,
egress_network: str = GATEWAY_EGRESS_NETWORK,
control_network: str = CONTROL_NETWORK,
repo_root: Path = _REPO_ROOT,
repo_root: Path | None = None,
) -> None:
self.image_ref = image_ref
self.name = name
self.network = network
self.egress_network = egress_network
self.control_network = control_network
self._repo_root = repo_root
# Build context: the repo root in a checkout, a staged copy from the
# installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
# Set by `connect_to_orchestrator`: the URL the daemons resolve policy
# against + the pre-minted `gateway` token they present. The gateway
# never mints, so it never holds the signing key (#469).
+5 -4
View File
@@ -24,6 +24,7 @@ from __future__ import annotations
from pathlib import Path
from ... import resources
from ...orchestrator.lifecycle import (
DEFAULT_PORT,
DEFAULT_STARTUP_TIMEOUT_SECONDS,
@@ -53,8 +54,6 @@ from .orchestrator import (
# still import it (probe / reprovision attribute against the gateway).
INFRA_NAME = GATEWAY_NAME
_REPO_ROOT = Path(__file__).resolve().parents[3]
class MacosInfraService(InfraService):
"""Composes the per-host orchestrator + gateway containers. Callers use
@@ -70,7 +69,7 @@ class MacosInfraService(InfraService):
control_network: str = CONTROL_NETWORK,
gateway_image: str = GATEWAY_IMAGE,
orchestrator_image: str = ORCHESTRATOR_IMAGE,
repo_root: Path = _REPO_ROOT,
repo_root: Path | None = None,
orchestrator_name: str = ORCHESTRATOR_NAME,
gateway_name: str = INFRA_NAME,
db_volume: str = ORCHESTRATOR_DB_VOLUME,
@@ -81,7 +80,9 @@ class MacosInfraService(InfraService):
self.control_network = control_network
self.gateway_image = gateway_image
self.orchestrator_image = orchestrator_image
self._repo_root = repo_root
# Build context / bind-mount source: the repo root in a checkout, a
# staged copy from the installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._orchestrator_name = orchestrator_name
self._gateway_name = gateway_name
self._db_volume = db_volume
+2 -3
View File
@@ -36,7 +36,6 @@ import dataclasses
import os
import subprocess
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...bottle_state import (
@@ -49,6 +48,7 @@ from ...git_gate import GitGate
from ...gateway.git_gate.http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
from ...image_cache import check_stale
from ...log import die, info, warn
from ... import resources
from .. import BottleImages
from ...supervisor.types import SUPERVISE_PORT
from ..docker.egress import EGRESS_PORT
@@ -71,7 +71,6 @@ from .consolidated_launch import (
deprovision_consolidated,
)
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
_AGENT_SLEEP_SECONDS = "2147483647"
@@ -94,7 +93,7 @@ def _agent_image(plan: MacosContainerBottlePlan) -> str:
)
info(f"using cached agent image {plan.image!r}")
return plan.image
container_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
container_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
return plan.image
@@ -18,6 +18,7 @@ import urllib.request
from pathlib import Path
from ... import log
from ... import resources
from ...paths import ORCHESTRATOR_TOKEN_ENV
from ...orchestrator.lifecycle import (
DEFAULT_HEALTH_TIMEOUT_SECONDS,
@@ -45,7 +46,6 @@ _DB_ROOT_IN_CONTAINER = "/var/lib/bot-bottle"
_SRC_IN_CONTAINER = "/bot-bottle-src"
_HEALTH_POLL_SECONDS = 0.25
_REPO_ROOT = Path(__file__).resolve().parents[3]
class MacosOrchestrator(Orchestrator):
@@ -61,7 +61,7 @@ class MacosOrchestrator(Orchestrator):
label: str = ORCHESTRATOR_LABEL,
port: int = DEFAULT_PORT,
control_network: str = CONTROL_NETWORK,
repo_root: Path = _REPO_ROOT,
repo_root: Path | None = None,
db_volume: str = ORCHESTRATOR_DB_VOLUME,
) -> None:
self.image_ref = image_ref
@@ -69,7 +69,9 @@ class MacosOrchestrator(Orchestrator):
self.label = label
self.port = port
self.control_network = control_network
self._repo_root = repo_root
# Build context / bind-mount source: the repo root in a checkout, a
# staged copy from the installed wheel otherwise (bot_bottle.resources).
self._repo_root = repo_root if repo_root is not None else resources.build_root()
self._db_volume = db_volume
def url(self) -> str:
-1
View File
@@ -62,7 +62,6 @@ GATEWAY_CA_GLOB = "mitmproxy-ca*"
# that lands. Env override matches the backend's BOT_BOTTLE_GATEWAY_IMAGE.
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
GATEWAY_DOCKERFILE = "Dockerfile.gateway"
REPO_ROOT = Path(__file__).resolve().parents[2]
def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:
+159
View File
@@ -0,0 +1,159 @@
"""Locate build-time resources whether bot-bottle runs from a source
checkout or an installed wheel.
The gateway / infra / orchestrator images are built from a Docker (or Apple
`container`) build context that must contain the `bot_bottle` package,
`pyproject.toml`, and the root-level Dockerfiles as siblings. In a source
checkout that context is simply the repo root, one level above the package.
An installed wheel has no repo root: the same root-level files are shipped
inside the package under ``bot_bottle/_resources/`` (see ``setup.py``), and a
repo-root-shaped build context is staged on demand into the app-data dir.
``build_root()`` is the single source of truth it returns a directory laid
out like a repo root (has ``bot_bottle/``, ``pyproject.toml``, the
Dockerfiles, ``nix/``, ``scripts/``). Every caller that needs a build
context, a Dockerfile path, the nix netpool module, or the netpool script
derives from it, so checkout and wheel installs share one downstream path.
"""
from __future__ import annotations
import fcntl
import hashlib
import os
import shutil
import tempfile
from pathlib import Path
from .paths import bot_bottle_root
_PKG = Path(__file__).resolve().parent # …/bot_bottle
_CHECKOUT_ROOT = _PKG.parent # repo root in a checkout
_BUNDLED = _PKG / "_resources" # wheel-shipped copies
# Root-level files bundled into the wheel under ``_resources/`` (paths are
# relative to the checkout root, and preserved verbatim under ``_resources/``
# and in the staged build root). ``setup.py`` copies exactly this set; keep
# the two lists in sync (``test_resources`` guards that every entry exists).
BUNDLED_RESOURCES: tuple[str, ...] = (
"pyproject.toml",
"Dockerfile.gateway",
"Dockerfile.orchestrator",
"Dockerfile.orchestrator.fc",
"nix/firecracker-netpool.nix",
"scripts/firecracker-netpool.sh",
)
# Present at a checkout root, never in a bare installed package — the cheap
# tell for which layout we're in.
_CHECKOUT_MARKER = "Dockerfile.gateway"
class ResourceError(RuntimeError):
"""Build resources are missing from the install (corrupt/partial wheel)."""
def is_source_checkout() -> bool:
"""True when running from a source tree (the root Dockerfiles sit beside
the package); False from an installed wheel."""
return (_CHECKOUT_ROOT / _CHECKOUT_MARKER).is_file()
def build_root() -> Path:
"""A directory shaped like a repo root: ``bot_bottle/``, ``pyproject.toml``,
the root Dockerfiles, ``nix/``, and ``scripts/``.
A checkout returns the repo root itself (no copying). An installed wheel
returns a staged copy under the app-data dir, materialized once and reused.
The stage is keyed by a digest of the installed package + bundled resources
(not the distribution version), so a force-reinstall of a newer commit that
keeps ``version = 0.1.0`` still rebuilds instead of reusing a stale tree."""
if is_source_checkout():
return _CHECKOUT_ROOT
return _stage_build_root()
def dockerfile(name: str) -> Path:
"""Absolute path to a root-level Dockerfile, e.g. ``Dockerfile.gateway``."""
return build_root() / name
def nix_netpool_module() -> Path:
"""Absolute path to the firecracker netpool NixOS module."""
return build_root() / "nix" / "firecracker-netpool.nix"
def netpool_script() -> Path:
"""Absolute path to the firecracker netpool bring-up script."""
return build_root() / "scripts" / "firecracker-netpool.sh"
def _content_digest() -> str:
"""A 16-hex digest of the installed package + bundled resources.
Keys the staged build root by *content*, so a force-reinstall over the same
version string (the installer defaults to a git branch + ``pipx install
--force``, and ``version`` stays ``0.1.0``) yields a different key and
re-stages, rather than reusing an old commit's tree. ``_PKG`` already
contains ``_resources``, so walking it covers both."""
h = hashlib.sha256()
for path in sorted(_PKG.rglob("*")):
if not path.is_file() or "__pycache__" in path.parts or path.suffix == ".pyc":
continue
h.update(str(path.relative_to(_PKG)).encode())
h.update(b"\0")
h.update(path.read_bytes())
return h.hexdigest()[:16]
def _stage_build_root() -> Path:
"""Materialize a repo-root-shaped build context from the installed wheel's
bundled resources, keyed by content digest. Idempotent and concurrency-safe:
a file lock serializes staging, a partial/stale tree is replaced, and the
finished tree is published with an atomic rename."""
if not _BUNDLED.is_dir():
raise ResourceError(
"bot-bottle build resources are missing from this install "
f"(expected {_BUNDLED}). Reinstall the package."
)
base = bot_bottle_root() / "build-root"
base.mkdir(parents=True, exist_ok=True)
dest = base / _content_digest()
if (dest / ".complete").is_file():
return dest
# Serialize staging across processes: a concurrent `start` after an install
# must not race on the shared tree. The lock is held only around stage +
# atomic publish; the fast path above never blocks.
with open(base / ".stage.lock", "w", encoding="utf-8") as lock:
fcntl.flock(lock, fcntl.LOCK_EX)
if (dest / ".complete").is_file(): # another process staged while we waited
return dest
# Stage into a private temp dir on the same filesystem, then publish by
# rename — never populate a shared path other processes might read.
staging = Path(tempfile.mkdtemp(prefix=".staging-", dir=base))
try:
# The package itself, minus caches and the bundled-resource copies,
# so the staged ``bot_bottle/`` matches a checkout's (keeps the
# firecracker infra-artifact hash stable across checkout and wheel).
shutil.copytree(
_PKG,
staging / "bot_bottle",
ignore=shutil.ignore_patterns("__pycache__", "*.pyc", "_resources"),
)
# The bundled root files, restored to their checkout-relative layout.
for rel in BUNDLED_RESOURCES:
dst = staging / rel
dst.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(_BUNDLED / rel, dst)
(staging / ".complete").write_text("")
# Replace any partial leftover for this digest (safe: we hold the
# lock), then publish atomically.
if dest.exists():
shutil.rmtree(dest)
os.replace(staging, dest)
staging = None # published; nothing to clean up
finally:
if staging is not None:
shutil.rmtree(staging, ignore_errors=True)
return dest